linux-sg2042/include/trace/ftrace.h

860 lines
24 KiB
C
Raw Normal View History

/*
* Stage 1 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
* struct ftrace_raw_<call> {
* struct trace_entry ent;
* <type> <item>;
* <type2> <item2>[<len>];
* [...]
* };
*
* The <type> <item> is created by the __field(type, item) macro or
* the __array(type2, item2, len) macro.
* We simply do "type item;", and that will create the fields
* in the structure.
*/
#include <linux/ftrace_event.h>
#ifndef TRACE_SYSTEM_VAR
#define TRACE_SYSTEM_VAR TRACE_SYSTEM
#endif
#define __app__(x, y) str__##x##y
#define __app(x, y) __app__(x, y)
#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name)
#define TRACE_MAKE_SYSTEM_STR() \
static const char TRACE_SYSTEM_STRING[] = \
__stringify(TRACE_SYSTEM)
TRACE_MAKE_SYSTEM_STR();
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
#undef TRACE_DEFINE_ENUM
#define TRACE_DEFINE_ENUM(a) \
static struct trace_enum_map __used __initdata \
__##TRACE_SYSTEM##_##a = \
{ \
.system = TRACE_SYSTEM_STRING, \
.enum_string = #a, \
.enum_value = a \
}; \
static struct trace_enum_map __used \
__attribute__((section("_ftrace_enum_map"))) \
*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
/*
* DECLARE_EVENT_CLASS can be used to add a generic function
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
* handlers for events. That is, if all events have the same
* parameters and just have distinct trace points.
* Each tracepoint can be defined with DEFINE_EVENT and that
* will map the DECLARE_EVENT_CLASS to the tracepoint.
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
*
* TRACE_EVENT is a one to one mapping between tracepoint and template.
*/
#undef TRACE_EVENT
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
DECLARE_EVENT_CLASS(name, \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
PARAMS(proto), \
PARAMS(args), \
PARAMS(tstruct), \
PARAMS(assign), \
PARAMS(print)); \
DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
#undef __field
#define __field(type, item) type item;
#undef __field_ext
#define __field_ext(type, item, filter_type) type item;
#undef __field_struct
#define __field_struct(type, item) type item;
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type) type item;
#undef __array
#define __array(type, item, len) type item[len];
#undef __dynamic_array
#define __dynamic_array(type, item, len) u32 __data_loc_##item;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
#undef TP_STRUCT__entry
#define TP_STRUCT__entry(args...) args
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
struct ftrace_raw_##name { \
struct trace_entry ent; \
tstruct \
char __data[0]; \
}; \
\
static struct ftrace_event_class event_class_##name;
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) event_##name
#undef DEFINE_EVENT_FN
#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
tracing: Move tracepoint callbacks from declaration to definition It's not strictly correct for the tracepoint reg/unreg callbacks to occur when a client is hooking up, because the actual tracepoint may not be present yet. This happens to be fine for syscall, since that's in the core kernel, but it would cause problems for tracepoints defined in a module that hasn't been loaded yet. It also means the reg/unreg has to be EXPORTed for any modules to use the tracepoint (as in SystemTap). This patch removes DECLARE_TRACE_WITH_CALLBACK, and instead introduces DEFINE_TRACE_FN which stores the callbacks in struct tracepoint. The callbacks are used now when the active state of the tracepoint changes in set_tracepoint & disable_tracepoint. This also introduces TRACE_EVENT_FN, so ftrace events can also provide registration callbacks if needed. Signed-off-by: Josh Stone <jistone@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Martin Bligh <mbligh@google.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> LKML-Reference: <1251150194-1713-4-git-send-email-jistone@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-08-25 05:43:13 +08:00
/* Callbacks are meaningless to ftrace. */
#undef TRACE_EVENT_FN
#define TRACE_EVENT_FN(name, proto, args, tstruct, \
assign, print, reg, unreg) \
TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \
PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \
tracing: Move tracepoint callbacks from declaration to definition It's not strictly correct for the tracepoint reg/unreg callbacks to occur when a client is hooking up, because the actual tracepoint may not be present yet. This happens to be fine for syscall, since that's in the core kernel, but it would cause problems for tracepoints defined in a module that hasn't been loaded yet. It also means the reg/unreg has to be EXPORTed for any modules to use the tracepoint (as in SystemTap). This patch removes DECLARE_TRACE_WITH_CALLBACK, and instead introduces DEFINE_TRACE_FN which stores the callbacks in struct tracepoint. The callbacks are used now when the active state of the tracepoint changes in set_tracepoint & disable_tracepoint. This also introduces TRACE_EVENT_FN, so ftrace events can also provide registration callbacks if needed. Signed-off-by: Josh Stone <jistone@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Martin Bligh <mbligh@google.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> LKML-Reference: <1251150194-1713-4-git-send-email-jistone@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-08-25 05:43:13 +08:00
#undef TRACE_EVENT_FLAGS
#define TRACE_EVENT_FLAGS(name, value) \
__TRACE_EVENT_FLAGS(name, value)
#undef TRACE_EVENT_PERF_PERM
#define TRACE_EVENT_PERF_PERM(name, expr...) \
__TRACE_EVENT_PERF_PERM(name, expr)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* Stage 2 of the trace events.
*
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
* Include the following:
*
* struct ftrace_data_offsets_<call> {
* u32 <item1>;
* u32 <item2>;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
* [...]
* };
*
* The __dynamic_array() macro will create each u32 <item>, this is
* to keep the offset of each array from the beginning of the event.
* The size of an array is also encoded, in the higher 16 bits of <item>.
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
*/
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
#undef TRACE_DEFINE_ENUM
#define TRACE_DEFINE_ENUM(a)
#undef __field
#define __field(type, item)
#undef __field_ext
#define __field_ext(type, item, filter_type)
#undef __field_struct
#define __field_struct(type, item)
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) u32 item;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
struct ftrace_data_offsets_##call { \
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tstruct; \
};
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#undef TRACE_EVENT_FLAGS
#define TRACE_EVENT_FLAGS(event, flag)
#undef TRACE_EVENT_PERF_PERM
#define TRACE_EVENT_PERF_PERM(event, expr...)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* Stage 3 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
* enum print_line_t
* ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
* {
* struct trace_seq *s = &iter->seq;
* struct ftrace_raw_<call> *field; <-- defined in stage 1
* struct trace_entry *entry;
* struct trace_seq *p = &iter->tmp_seq;
* int ret;
*
* entry = iter->ent;
*
* if (entry->type != event_<call>->event.type) {
* WARN_ON_ONCE(1);
* return TRACE_TYPE_UNHANDLED;
* }
*
* field = (typeof(field))entry;
*
* trace_seq_init(p);
* ret = trace_seq_printf(s, "%s: ", <call>);
* if (ret)
* ret = trace_seq_printf(s, <TP_printk> "\n");
* if (!ret)
* return TRACE_TYPE_PARTIAL_LINE;
*
* return TRACE_TYPE_HANDLED;
* }
*
* This is the method used to print the raw event to the trace
* output format. Note, this is not needed if the data is read
* in binary.
*/
#undef __entry
#define __entry field
#undef TP_printk
#define TP_printk(fmt, args...) fmt "\n", args
#undef __get_dynamic_array
#define __get_dynamic_array(field) \
((void *)__entry + (__entry->__data_loc_##field & 0xffff))
#undef __get_dynamic_array_len
#define __get_dynamic_array_len(field) \
((__entry->__data_loc_##field >> 16) & 0xffff)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __get_bitmask
#define __get_bitmask(field) \
({ \
void *__bitmask = __get_dynamic_array(field); \
unsigned int __bitmask_size; \
__bitmask_size = __get_dynamic_array_len(field); \
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
ftrace_print_bitmask_seq(p, __bitmask, __bitmask_size); \
})
#undef __print_flags
#define __print_flags(flag, delim, flag_array...) \
({ \
static const struct trace_print_flags __flags[] = \
{ flag_array, { -1, NULL }}; \
ftrace_print_flags_seq(p, delim, flag, __flags); \
})
#undef __print_symbolic
#define __print_symbolic(value, symbol_array...) \
({ \
static const struct trace_print_flags symbols[] = \
{ symbol_array, { -1, NULL }}; \
ftrace_print_symbols_seq(p, value, symbols); \
})
#undef __print_symbolic_u64
#if BITS_PER_LONG == 32
#define __print_symbolic_u64(value, symbol_array...) \
({ \
static const struct trace_print_flags_u64 symbols[] = \
{ symbol_array, { -1, NULL } }; \
ftrace_print_symbols_seq_u64(p, value, symbols); \
})
#else
#define __print_symbolic_u64(value, symbol_array...) \
__print_symbolic(value, symbol_array)
#endif
#undef __print_hex
#define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
#undef __print_array
#define __print_array(array, count, el_size) \
({ \
BUILD_BUG_ON(el_size != 1 && el_size != 2 && \
el_size != 4 && el_size != 8); \
ftrace_print_array_seq(p, array, count, el_size); \
})
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace enum print_line_t \
ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
struct trace_event *trace_event) \
{ \
struct trace_seq *s = &iter->seq; \
struct trace_seq __maybe_unused *p = &iter->tmp_seq; \
struct ftrace_raw_##call *field; \
int ret; \
\
field = (typeof(field))iter->ent; \
\
ret = ftrace_raw_output_prep(iter, trace_event); \
if (ret != TRACE_TYPE_HANDLED) \
return ret; \
\
trace_seq_printf(s, print); \
\
return trace_handle_return(s); \
} \
static struct trace_event_functions ftrace_event_type_funcs_##call = { \
.trace = ftrace_raw_output_##call, \
};
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
static notrace enum print_line_t \
ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
struct trace_event *event) \
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
{ \
struct ftrace_raw_##template *field; \
struct trace_entry *entry; \
struct trace_seq *p = &iter->tmp_seq; \
\
entry = iter->ent; \
\
if (entry->type != event_##call.event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
\
field = (typeof(field))entry; \
\
trace_seq_init(p); \
return ftrace_output_call(iter, #call, print); \
} \
static struct trace_event_functions ftrace_event_type_funcs_##call = { \
.trace = ftrace_raw_output_##call, \
};
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef __field_ext
#define __field_ext(type, item, filter_type) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), filter_type); \
if (ret) \
return ret;
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
0, filter_type); \
if (ret) \
return ret;
#undef __field
#define __field(type, item) __field_ext(type, item, FILTER_OTHER)
#undef __field_struct
#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
#undef __array
#define __array(type, item, len) \
do { \
tracing: Fix array size mismatch in format string In event format strings, the array size is reported in two locations. One in array subscript and then via the "size:" attribute. The values reported there have a mismatch. For e.g., in sched:sched_switch the prev_comm and next_comm character arrays have subscript values as [32] where as the actual field size is 16. name: sched_switch ID: 301 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; field:char prev_comm[32]; offset:8; size:16; signed:1; field:pid_t prev_pid; offset:24; size:4; signed:1; field:int prev_prio; offset:28; size:4; signed:1; field:long prev_state; offset:32; size:8; signed:1; field:char next_comm[32]; offset:40; size:16; signed:1; field:pid_t next_pid; offset:56; size:4; signed:1; field:int next_prio; offset:60; size:4; signed:1; After bisection, the following commit was blamed: 92edca0 tracing: Use direct field, type and system names This commit removes the duplication of strings for field->name and field->type assuming that all the strings passed in __trace_define_field() are immutable. This is not true for arrays, where the type string is created in event_storage variable and field->type for all array fields points to event_storage. Use __stringify() to create a string constant for the type string. Also, get rid of event_storage and event_storage_mutex that are not needed anymore. also, an added benefit is that this reduces the overhead of events a bit more: text data bss dec hex filename 8424787 2036472 1302528 11763787 b3804b vmlinux 8420814 2036408 1302528 11759750 b37086 vmlinux.patched Link: http://lkml.kernel.org/r/1392349908-29685-1-git-send-email-vnagarnaik@google.com Cc: Laurent Chavey <chavey@google.com> Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-02-14 11:51:48 +08:00
char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
tracing: Fix array size mismatch in format string In event format strings, the array size is reported in two locations. One in array subscript and then via the "size:" attribute. The values reported there have a mismatch. For e.g., in sched:sched_switch the prev_comm and next_comm character arrays have subscript values as [32] where as the actual field size is 16. name: sched_switch ID: 301 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; field:char prev_comm[32]; offset:8; size:16; signed:1; field:pid_t prev_pid; offset:24; size:4; signed:1; field:int prev_prio; offset:28; size:4; signed:1; field:long prev_state; offset:32; size:8; signed:1; field:char next_comm[32]; offset:40; size:16; signed:1; field:pid_t next_pid; offset:56; size:4; signed:1; field:int next_prio; offset:60; size:4; signed:1; After bisection, the following commit was blamed: 92edca0 tracing: Use direct field, type and system names This commit removes the duplication of strings for field->name and field->type assuming that all the strings passed in __trace_define_field() are immutable. This is not true for arrays, where the type string is created in event_storage variable and field->type for all array fields points to event_storage. Use __stringify() to create a string constant for the type string. Also, get rid of event_storage and event_storage_mutex that are not needed anymore. also, an added benefit is that this reduces the overhead of events a bit more: text data bss dec hex filename 8424787 2036472 1302528 11763787 b3804b vmlinux 8420814 2036408 1302528 11759750 b37086 vmlinux.patched Link: http://lkml.kernel.org/r/1392349908-29685-1-git-send-email-vnagarnaik@google.com Cc: Laurent Chavey <chavey@google.com> Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-02-14 11:51:48 +08:00
ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret; \
} while (0);
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
ret = trace_define_field(event_call, "__data_loc " #type "[]", #item, \
offsetof(typeof(field), __data_loc_##item), \
sizeof(field.__data_loc_##item), \
is_signed_type(type), FILTER_OTHER);
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \
static int notrace __init \
ftrace_define_fields_##call(struct ftrace_event_call *event_call) \
{ \
struct ftrace_raw_##call field; \
int ret; \
\
tstruct; \
\
return ret; \
}
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* remember the offset of each array from the beginning of the event.
*/
#undef __entry
#define __entry entry
#undef __field
#define __field(type, item)
#undef __field_ext
#define __field_ext(type, item, filter_type)
#undef __field_struct
#define __field_struct(type, item)
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type)
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
__item_length = (len) * sizeof(type); \
__data_offsets->item = __data_size + \
offsetof(typeof(*entry), __data); \
__data_offsets->item |= __item_length << 16; \
__data_size += __item_length;
#undef __string
tracing: Allow events to have NULL strings If an TRACE_EVENT() uses __assign_str() or __get_str on a NULL pointer then the following oops will happen: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<c127a17b>] strlen+0x10/0x1a *pde = 00000000 ^M Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.13.0-rc1-test+ #2 Hardware name: /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006^M task: f5cde9f0 ti: f5e5e000 task.ti: f5e5e000 EIP: 0060:[<c127a17b>] EFLAGS: 00210046 CPU: 1 EIP is at strlen+0x10/0x1a EAX: 00000000 EBX: c2472da8 ECX: ffffffff EDX: c2472da8 ESI: c1c5e5fc EDI: 00000000 EBP: f5e5fe84 ESP: f5e5fe80 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 00000000 CR3: 01f32000 CR4: 000007d0 Stack: f5f18b90 f5e5feb8 c10687a8 0759004f 00000005 00000005 00000005 00200046 00000002 00000000 c1082a93 f56c7e28 c2472da8 c1082a93 f5e5fee4 c106bc61^M 00000000 c1082a93 00000000 00000000 00000001 00200046 00200082 00000000 Call Trace: [<c10687a8>] ftrace_raw_event_lock+0x39/0xc0 [<c1082a93>] ? ktime_get+0x29/0x69 [<c1082a93>] ? ktime_get+0x29/0x69 [<c106bc61>] lock_release+0x57/0x1a5 [<c1082a93>] ? ktime_get+0x29/0x69 [<c10824dd>] read_seqcount_begin.constprop.7+0x4d/0x75 [<c1082a93>] ? ktime_get+0x29/0x69^M [<c1082a93>] ktime_get+0x29/0x69 [<c108a46a>] __tick_nohz_idle_enter+0x1e/0x426 [<c10690e8>] ? lock_release_holdtime.part.19+0x48/0x4d [<c10bc184>] ? time_hardirqs_off+0xe/0x28 [<c1068c82>] ? trace_hardirqs_off_caller+0x3f/0xaf [<c108a8cb>] tick_nohz_idle_enter+0x59/0x62 [<c1079242>] cpu_startup_entry+0x64/0x192 [<c102299c>] start_secondary+0x277/0x27c Code: 90 89 c6 89 d0 88 c4 ac 38 e0 74 09 84 c0 75 f7 be 01 00 00 00 89 f0 48 5e 5d c3 55 89 e5 57 66 66 66 66 90 83 c9 ff 89 c7 31 c0 <f2> ae f7 d1 8d 41 ff 5f 5d c3 55 89 e5 57 66 66 66 66 90 31 ff EIP: [<c127a17b>] strlen+0x10/0x1a SS:ESP 0068:f5e5fe80 CR2: 0000000000000000 ---[ end trace 01bc47bf519ec1b2 ]--- New tracepoints have been added that have allowed for NULL pointers being assigned to strings. To fix this, change the TRACE_EVENT() code to check for NULL and if it is, it will assign "(null)" to it instead (similar to what glibc printf does). Reported-by: Shuah Khan <shuah.kh@samsung.com> Reported-by: Jovi Zhangwei <jovi.zhangwei@gmail.com> Link: http://lkml.kernel.org/r/CAGdX0WFeEuy+DtpsJzyzn0343qEEjLX97+o1VREFkUEhndC+5Q@mail.gmail.com Link: http://lkml.kernel.org/r/528D6972.9010702@samsung.com Fixes: 9cbf117662e2 ("tracing/events: provide string with undefined size support") Cc: stable@vger.kernel.org # 2.6.31+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-11-26 22:22:54 +08:00
#define __string(item, src) __dynamic_array(char, item, \
strlen((src) ? (const char *)(src) : "(null)") + 1)
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
/*
* __bitmask_size_in_bytes_raw is the number of bytes needed to hold
* num_possible_cpus().
*/
#define __bitmask_size_in_bytes_raw(nr_bits) \
(((nr_bits) + 7) / 8)
#define __bitmask_size_in_longs(nr_bits) \
((__bitmask_size_in_bytes_raw(nr_bits) + \
((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8))
/*
* __bitmask_size_in_bytes is the number of bytes needed to hold
* num_possible_cpus() padded out to the nearest long. This is what
* is saved in the buffer, just to be consistent.
*/
#define __bitmask_size_in_bytes(nr_bits) \
(__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8))
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \
__bitmask_size_in_longs(nr_bits))
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static inline notrace int ftrace_get_offsets_##call( \
struct ftrace_data_offsets_##call *__data_offsets, proto) \
{ \
int __data_size = 0; \
int __maybe_unused __item_length; \
struct ftrace_raw_##call __maybe_unused *entry; \
\
tstruct; \
\
return __data_size; \
}
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
/*
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
* Stage 4 of the trace events.
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
*
* Override the macros in <trace/trace_events.h> to include the following:
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
*
* For those macros defined with TRACE_EVENT:
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
*
* static struct ftrace_event_call event_<call>;
*
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
* static void ftrace_raw_event_<call>(void *__data, proto)
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
* {
* struct ftrace_event_file *ftrace_file = __data;
* struct ftrace_event_call *event_call = ftrace_file->event_call;
* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
tracing: Add and use generic set_trigger_filter() implementation Add a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters. Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command: echo 'enable_event:system:event if common_pid == 999' > \ .../othersys/otherevent/trigger The above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999. As another example, to add a filter to a stacktrace command: echo 'stacktrace if common_pid == 999' > \ .../somesys/someevent/trigger The above command will only trigger a stacktrace if the common_pid field in the event is 999. The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt. Because triggers can now use filters, the trigger-invoking logic needs to be moved in those cases - e.g. for ftrace_raw_event_calls, if a trigger has a filter associated with it, the trigger invocation now needs to happen after the { assign; } part of the call, in order for the trigger condition to be tested. There's still a SOFT_DISABLED-only check at the top of e.g. the ftrace_raw_events function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged. There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call(). To simplify the above and make it more efficient, the TRIGGER_COND bit is introduced, which is set only if a soft-disabled trigger needs to use the log record for filter testing or needs to wait until the current log record is closed. The syscall event invocation code is also changed in analogous ways. Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves. Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:59:29 +08:00
* unsigned long eflags = ftrace_file->flags;
* enum event_trigger_type __tt = ETT_NONE;
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
* struct ring_buffer *buffer;
* unsigned long irq_flags;
* int __data_size;
* int pc;
*
tracing: Add and use generic set_trigger_filter() implementation Add a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters. Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command: echo 'enable_event:system:event if common_pid == 999' > \ .../othersys/otherevent/trigger The above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999. As another example, to add a filter to a stacktrace command: echo 'stacktrace if common_pid == 999' > \ .../somesys/someevent/trigger The above command will only trigger a stacktrace if the common_pid field in the event is 999. The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt. Because triggers can now use filters, the trigger-invoking logic needs to be moved in those cases - e.g. for ftrace_raw_event_calls, if a trigger has a filter associated with it, the trigger invocation now needs to happen after the { assign; } part of the call, in order for the trigger condition to be tested. There's still a SOFT_DISABLED-only check at the top of e.g. the ftrace_raw_events function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged. There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call(). To simplify the above and make it more efficient, the TRIGGER_COND bit is introduced, which is set only if a soft-disabled trigger needs to use the log record for filter testing or needs to wait until the current log record is closed. The syscall event invocation code is also changed in analogous ways. Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves. Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:59:29 +08:00
* if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
* if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
* event_triggers_call(ftrace_file, NULL);
* if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
* return;
* }
*
* local_save_flags(irq_flags);
* pc = preempt_count();
*
* __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
*
* event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,
* event_<call>->event.type,
* sizeof(*entry) + __data_size,
* irq_flags, pc);
* if (!event)
* return;
* entry = ring_buffer_event_data(event);
*
* { <assign>; } <-- Here we assign the entries by the __field and
* __array macros.
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
*
tracing: Add and use generic set_trigger_filter() implementation Add a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters. Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command: echo 'enable_event:system:event if common_pid == 999' > \ .../othersys/otherevent/trigger The above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999. As another example, to add a filter to a stacktrace command: echo 'stacktrace if common_pid == 999' > \ .../somesys/someevent/trigger The above command will only trigger a stacktrace if the common_pid field in the event is 999. The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt. Because triggers can now use filters, the trigger-invoking logic needs to be moved in those cases - e.g. for ftrace_raw_event_calls, if a trigger has a filter associated with it, the trigger invocation now needs to happen after the { assign; } part of the call, in order for the trigger condition to be tested. There's still a SOFT_DISABLED-only check at the top of e.g. the ftrace_raw_events function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged. There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call(). To simplify the above and make it more efficient, the TRIGGER_COND bit is introduced, which is set only if a soft-disabled trigger needs to use the log record for filter testing or needs to wait until the current log record is closed. The syscall event invocation code is also changed in analogous ways. Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves. Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:59:29 +08:00
* if (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
* __tt = event_triggers_call(ftrace_file, entry);
*
* if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
* &ftrace_file->flags))
* ring_buffer_discard_commit(buffer, event);
* else if (!filter_check_discard(ftrace_file, entry, buffer, event))
tracing: Update event filters for multibuffer The trace event filters are still tied to event calls rather than event files, which means you don't get what you'd expect when using filters in the multibuffer case: Before: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 2048 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 Setting the filter in tracing/instances/test1/events shouldn't affect the same event in tracing/events as it does above. After: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 We'd like to just move the filter directly from ftrace_event_call to ftrace_event_file, but there are a couple cases that don't yet have multibuffer support and therefore have to continue using the current event_call-based filters. For those cases, a new USE_CALL_FILTER bit is added to the event_call flags, whose main purpose is to keep the old behavior for those cases until they can be updated with multibuffer support; at that point, the USE_CALL_FILTER flag (and the new associated call_filter_check_discard() function) can go away. The multibuffer support also made filter_current_check_discard() redundant, so this change removes that function as well and replaces it with filter_check_discard() (or call_filter_check_discard() as appropriate). Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:34:17 +08:00
* trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
tracing: Add and use generic set_trigger_filter() implementation Add a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters. Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command: echo 'enable_event:system:event if common_pid == 999' > \ .../othersys/otherevent/trigger The above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999. As another example, to add a filter to a stacktrace command: echo 'stacktrace if common_pid == 999' > \ .../somesys/someevent/trigger The above command will only trigger a stacktrace if the common_pid field in the event is 999. The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt. Because triggers can now use filters, the trigger-invoking logic needs to be moved in those cases - e.g. for ftrace_raw_event_calls, if a trigger has a filter associated with it, the trigger invocation now needs to happen after the { assign; } part of the call, in order for the trigger condition to be tested. There's still a SOFT_DISABLED-only check at the top of e.g. the ftrace_raw_events function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged. There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call(). To simplify the above and make it more efficient, the TRIGGER_COND bit is introduced, which is set only if a soft-disabled trigger needs to use the log record for filter testing or needs to wait until the current log record is closed. The syscall event invocation code is also changed in analogous ways. Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves. Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:59:29 +08:00
*
* if (__tt)
* event_triggers_post_call(ftrace_file, __tt);
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
* }
*
* static struct trace_event ftrace_event_type_<call> = {
* .trace = ftrace_raw_output_<call>, <-- stage 2
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
* };
*
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
* static char print_fmt_<call>[] = <TP_printk>;
*
* static struct ftrace_event_class __used event_class_<template> = {
* .system = "<system>",
tracing: Move fields from event to class structure Move the defined fields from the event to the class structure. Since the fields of the event are defined by the class they belong to, it makes sense to have the class hold the information instead of the individual events. The events of the same class would just hold duplicate information. After this change the size of the kernel dropped another 3K: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900252 1057412 861512 6819176 680d68 vmlinux.regs 4900375 1053380 861512 6815267 67fe23 vmlinux.fields Although the text increased, this was mainly due to the C files having to adapt to the change. This is a constant increase, where new tracepoints will not increase the Text. But the big drop is in the data size (as well as needed allocations to hold the fields). This will give even more savings as more tracepoints are created. Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS() with several DEFINE_EVENT()s, then the savings will be lost. But we are pushing developers to consolidate events with DEFINE_EVENT() so this should not be an issue. The kprobes define a unique class to every new event, but are dynamic so it should not be a issue. The syscalls however have a single class but the fields for the individual events are different. The syscalls use a metadata to define the fields. I moved the fields list from the event to the metadata and added a "get_fields()" function to the class. This function is used to find the fields. For normal events and kprobes, get_fields() just returns a pointer to the fields list_head in the class. For syscall events, it returns the fields list_head in the metadata for the event. v2: Fixed the syscall fields. The syscall metadata needs a list of fields for both enter and exit. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 22:35:55 +08:00
* .define_fields = ftrace_define_fields_<call>,
* .fields = LIST_HEAD_INIT(event_class_##call.fields),
* .raw_init = trace_event_raw_init,
* .probe = ftrace_raw_event_##call,
* .reg = ftrace_event_reg,
* };
*
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
* static struct ftrace_event_call event_<call> = {
* .class = event_class_<template>,
* {
* .tp = &__tracepoint_<call>,
* },
tracing: Move fields from event to class structure Move the defined fields from the event to the class structure. Since the fields of the event are defined by the class they belong to, it makes sense to have the class hold the information instead of the individual events. The events of the same class would just hold duplicate information. After this change the size of the kernel dropped another 3K: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900252 1057412 861512 6819176 680d68 vmlinux.regs 4900375 1053380 861512 6815267 67fe23 vmlinux.fields Although the text increased, this was mainly due to the C files having to adapt to the change. This is a constant increase, where new tracepoints will not increase the Text. But the big drop is in the data size (as well as needed allocations to hold the fields). This will give even more savings as more tracepoints are created. Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS() with several DEFINE_EVENT()s, then the savings will be lost. But we are pushing developers to consolidate events with DEFINE_EVENT() so this should not be an issue. The kprobes define a unique class to every new event, but are dynamic so it should not be a issue. The syscalls however have a single class but the fields for the individual events are different. The syscalls use a metadata to define the fields. I moved the fields list from the event to the metadata and added a "get_fields()" function to the class. This function is used to find the fields. For normal events and kprobes, get_fields() just returns a pointer to the fields list_head in the class. For syscall events, it returns the fields list_head in the metadata for the event. v2: Fixed the syscall fields. The syscall metadata needs a list of fields for both enter and exit. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 22:35:55 +08:00
* .event = &ftrace_event_type_<call>,
* .print_fmt = print_fmt_<call>,
* .flags = TRACE_EVENT_FL_TRACEPOINT,
* };
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
* // its only safe to use pointers when doing linker tricks to
* // create an array.
* static struct ftrace_event_call __used
* __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
*
*/
#ifdef CONFIG_PERF_EVENTS
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
#define _TRACE_PERF_PROTO(call, proto) \
static notrace void \
perf_trace_##call(void *__data, proto);
#define _TRACE_PERF_INIT(call) \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
.perf_probe = perf_trace_##call,
#else
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
#define _TRACE_PERF_PROTO(call, proto)
#define _TRACE_PERF_INIT(call)
#endif /* CONFIG_PERF_EVENTS */
tracing: new format for specialized trace points Impact: clean up and enhancement The TRACE_EVENT_FORMAT macro looks quite ugly and is limited in its ability to save data as well as to print the record out. Working with Ingo Molnar, we came up with a new format that is much more pleasing to the eye of C developers. This new macro is more C style than the old macro, and is more obvious to what it does. Here's the example. The only updated macro in this patch is the sched_switch trace point. The old method looked like this: TRACE_EVENT_FORMAT(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next), TP_ARGS(rq, prev, next), TP_FMT("task %s:%d ==> %s:%d", prev->comm, prev->pid, next->comm, next->pid), TRACE_STRUCT( TRACE_FIELD(pid_t, prev_pid, prev->pid) TRACE_FIELD(int, prev_prio, prev->prio) TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN], next_comm, TP_CMD(memcpy(TRACE_ENTRY->next_comm, next->comm, TASK_COMM_LEN))) TRACE_FIELD(pid_t, next_pid, next->pid) TRACE_FIELD(int, next_prio, next->prio) ), TP_RAW_FMT("prev %d:%d ==> next %s:%d:%d") ); The above method is hard to read and requires two format fields. The new method: /* * Tracepoint for task switches, performed by the scheduler: * * (NOTE: the 'rq' argument is not used by generic trace events, * but used by the latency tracer plugin. ) */ TRACE_EVENT(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next), TP_ARGS(rq, prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) __field( pid_t, prev_pid ) __field( int, prev_prio ) __array( char, next_comm, TASK_COMM_LEN ) __field( pid_t, next_pid ) __field( int, next_prio ) ), TP_printk("task %s:%d [%d] ==> %s:%d [%d]", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, __entry->next_comm, __entry->next_pid, __entry->next_prio), TP_fast_assign( memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; ) ); This macro is called TRACE_EVENT, it is broken up into 5 parts: TP_PROTO: the proto type of the trace point TP_ARGS: the arguments of the trace point TP_STRUCT_entry: the structure layout of the entry in the ring buffer TP_printk: the printk format TP_fast_assign: the method used to write the entry into the ring buffer The structure is the definition of how the event will be saved in the ring buffer. The printk is used by the internal tracing in case of an oops, and the kernel needs to print out the format of the record to the console. This the TP_printk gives a means to show the records in a human readable format. It is also used to print out the data from the trace file. The TP_fast_assign is executed directly. It is basically like a C function, where the __entry is the handle to the record. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-10 05:14:30 +08:00
#undef __entry
#define __entry entry
tracing: add TRACE_FIELD_SPECIAL to record complex entries Tom Zanussi pointed out that the simple TRACE_FIELD was not enough to record trace data that required memcpy. This patch addresses this issue by adding a TRACE_FIELD_SPECIAL. The format is similar to TRACE_FIELD but looks like so: TRACE_FIELD_SPECIAL(type_item, item, cmd) What TRACE_FIELD gave was: TRACE_FIELD(type, item, assign) The TRACE_FIELD would be used in declaring a structure: struct { type item; }; And later assign it via: entry->item = assign; What TRACE_FIELD_SPECIAL gives us is: In the declaration of the structure: struct { type_item; }; And the assignment: cmd; This change log will explain the one example used in the patch: TRACE_EVENT_FORMAT(sched_switch, TPPROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next), TPARGS(rq, prev, next), TPFMT("task %s:%d ==> %s:%d", prev->comm, prev->pid, next->comm, next->pid), TRACE_STRUCT( TRACE_FIELD(pid_t, prev_pid, prev->pid) TRACE_FIELD(int, prev_prio, prev->prio) TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN], next_comm, TPCMD(memcpy(TRACE_ENTRY->next_comm, next->comm, TASK_COMM_LEN))) TRACE_FIELD(pid_t, next_pid, next->pid) TRACE_FIELD(int, next_prio, next->prio) ), TPRAWFMT("prev %d:%d ==> next %s:%d:%d") ); The struct will be create as: struct { pid_t prev_pid; int prev_prio; char next_comm[TASK_COMM_LEN]; pid_t next_pid; int next_prio; }; Note the TRACE_ENTRY in the cmd part of TRACE_SPECIAL. TRACE_ENTRY will be set by the tracer to point to the structure inside the trace buffer. entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; memcpy(entry->next_comm, next->comm, TASK_COMM_LEN); entry->next_pid = next->pid; entry->next_prio = next->prio Reported-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-02 23:53:15 +08:00
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __field
#define __field(type, item)
#undef __field_struct
#define __field_struct(type, item)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
__entry->__data_loc_##item = __data_offsets.item;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __assign_str
#define __assign_str(dst, src) \
tracing: Allow events to have NULL strings If an TRACE_EVENT() uses __assign_str() or __get_str on a NULL pointer then the following oops will happen: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<c127a17b>] strlen+0x10/0x1a *pde = 00000000 ^M Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.13.0-rc1-test+ #2 Hardware name: /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006^M task: f5cde9f0 ti: f5e5e000 task.ti: f5e5e000 EIP: 0060:[<c127a17b>] EFLAGS: 00210046 CPU: 1 EIP is at strlen+0x10/0x1a EAX: 00000000 EBX: c2472da8 ECX: ffffffff EDX: c2472da8 ESI: c1c5e5fc EDI: 00000000 EBP: f5e5fe84 ESP: f5e5fe80 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 00000000 CR3: 01f32000 CR4: 000007d0 Stack: f5f18b90 f5e5feb8 c10687a8 0759004f 00000005 00000005 00000005 00200046 00000002 00000000 c1082a93 f56c7e28 c2472da8 c1082a93 f5e5fee4 c106bc61^M 00000000 c1082a93 00000000 00000000 00000001 00200046 00200082 00000000 Call Trace: [<c10687a8>] ftrace_raw_event_lock+0x39/0xc0 [<c1082a93>] ? ktime_get+0x29/0x69 [<c1082a93>] ? ktime_get+0x29/0x69 [<c106bc61>] lock_release+0x57/0x1a5 [<c1082a93>] ? ktime_get+0x29/0x69 [<c10824dd>] read_seqcount_begin.constprop.7+0x4d/0x75 [<c1082a93>] ? ktime_get+0x29/0x69^M [<c1082a93>] ktime_get+0x29/0x69 [<c108a46a>] __tick_nohz_idle_enter+0x1e/0x426 [<c10690e8>] ? lock_release_holdtime.part.19+0x48/0x4d [<c10bc184>] ? time_hardirqs_off+0xe/0x28 [<c1068c82>] ? trace_hardirqs_off_caller+0x3f/0xaf [<c108a8cb>] tick_nohz_idle_enter+0x59/0x62 [<c1079242>] cpu_startup_entry+0x64/0x192 [<c102299c>] start_secondary+0x277/0x27c Code: 90 89 c6 89 d0 88 c4 ac 38 e0 74 09 84 c0 75 f7 be 01 00 00 00 89 f0 48 5e 5d c3 55 89 e5 57 66 66 66 66 90 83 c9 ff 89 c7 31 c0 <f2> ae f7 d1 8d 41 ff 5f 5d c3 55 89 e5 57 66 66 66 66 90 31 ff EIP: [<c127a17b>] strlen+0x10/0x1a SS:ESP 0068:f5e5fe80 CR2: 0000000000000000 ---[ end trace 01bc47bf519ec1b2 ]--- New tracepoints have been added that have allowed for NULL pointers being assigned to strings. To fix this, change the TRACE_EVENT() code to check for NULL and if it is, it will assign "(null)" to it instead (similar to what glibc printf does). Reported-by: Shuah Khan <shuah.kh@samsung.com> Reported-by: Jovi Zhangwei <jovi.zhangwei@gmail.com> Link: http://lkml.kernel.org/r/CAGdX0WFeEuy+DtpsJzyzn0343qEEjLX97+o1VREFkUEhndC+5Q@mail.gmail.com Link: http://lkml.kernel.org/r/528D6972.9010702@samsung.com Fixes: 9cbf117662e2 ("tracing/events: provide string with undefined size support") Cc: stable@vger.kernel.org # 2.6.31+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-11-26 22:22:54 +08:00
strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef __get_bitmask
#define __get_bitmask(field) (char *)__get_dynamic_array(field)
#undef __assign_bitmask
#define __assign_bitmask(dst, src, nr_bits) \
memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
#undef TP_fast_assign
#define TP_fast_assign(args...) args
#undef __perf_addr
#define __perf_addr(a) (a)
#undef __perf_count
#define __perf_count(c) (c)
#undef __perf_task
#define __perf_task(t) (t)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
\
static notrace void \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
ftrace_raw_event_##call(void *__data, proto) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
{ \
struct ftrace_event_file *ftrace_file = __data; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ftrace_event_buffer fbuffer; \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
struct ftrace_raw_##call *entry; \
int __data_size; \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
\
if (ftrace_trigger_soft_disabled(ftrace_file)) \
return; \
\
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
\
entry = ftrace_event_buffer_reserve(&fbuffer, ftrace_file, \
sizeof(*entry) + __data_size); \
\
if (!entry) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
return; \
\
tstruct \
\
{ assign; } \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
\
ftrace_event_buffer_commit(&fbuffer); \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
}
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
/*
* The ftrace_test_probe is compiled out, it is only here as a build time check
* to make sure that if the tracepoint handling changes, the ftrace probe will
* fail to compile unless it too is updated.
*/
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
static inline void ftrace_test_probe_##call(void) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
{ \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
check_trace_callback_type_##call(ftrace_raw_event_##template); \
}
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef __entry
#define __entry REC
#undef __print_flags
#undef __print_symbolic
tracing/kvm: Use __print_hex() for kvm_emulate_insn tracepoint The kvm_emulate_insn tracepoint used __print_insn() for printing its instructions. However it makes the format of the event hard to parse as it reveals TP internals. Fortunately, kernel provides __print_hex for almost same purpose, we can use it instead of open coding it. The user-space can be changed to parse it later. That means raw kernel tracing will not be affected by this change: # cd /sys/kernel/debug/tracing/ # cat events/kvm/kvm_emulate_insn/format name: kvm_emulate_insn ID: 29 format: ... print fmt: "%x:%llx:%s (%s)%s", REC->csbase, REC->rip, __print_hex(REC->insn, REC->len), \ __print_symbolic(REC->flags, { 0, "real" }, { (1 << 0) | (1 << 1), "vm16" }, \ { (1 << 0), "prot16" }, { (1 << 0) | (1 << 2), "prot32" }, { (1 << 0) | (1 << 3), "prot64" }), \ REC->failed ? " failed" : "" # echo 1 > events/kvm/kvm_emulate_insn/enable # cat trace # tracer: nop # # entries-in-buffer/entries-written: 2183/2183 #P:12 # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | qemu-kvm-1782 [002] ...1 140.931636: kvm_emulate_insn: 0:c102fa25:89 10 (prot32) qemu-kvm-1781 [004] ...1 140.931637: kvm_emulate_insn: 0:c102fa25:89 10 (prot32) Link: http://lkml.kernel.org/n/tip-wfw6y3b9ugtey8snaow9nmg5@git.kernel.org Link: http://lkml.kernel.org/r/1340757701-10711-2-git-send-email-namhyung@kernel.org Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@kernel.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: kvm@vger.kernel.org Acked-by: Avi Kivity <avi@redhat.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-06-27 08:41:39 +08:00
#undef __print_hex
#undef __get_dynamic_array
#undef __get_dynamic_array_len
#undef __get_str
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __get_bitmask
#undef __print_array
#undef TP_printk
#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
_TRACE_PERF_PROTO(call, PARAMS(proto)); \
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
static char print_fmt_##call[] = print; \
static struct ftrace_event_class __used __refdata event_class_##call = { \
.system = TRACE_SYSTEM_STRING, \
tracing: Move fields from event to class structure Move the defined fields from the event to the class structure. Since the fields of the event are defined by the class they belong to, it makes sense to have the class hold the information instead of the individual events. The events of the same class would just hold duplicate information. After this change the size of the kernel dropped another 3K: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4900252 1057412 861512 6819176 680d68 vmlinux.regs 4900375 1053380 861512 6815267 67fe23 vmlinux.fields Although the text increased, this was mainly due to the C files having to adapt to the change. This is a constant increase, where new tracepoints will not increase the Text. But the big drop is in the data size (as well as needed allocations to hold the fields). This will give even more savings as more tracepoints are created. Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS() with several DEFINE_EVENT()s, then the savings will be lost. But we are pushing developers to consolidate events with DEFINE_EVENT() so this should not be an issue. The kprobes define a unique class to every new event, but are dynamic so it should not be a issue. The syscalls however have a single class but the fields for the individual events are different. The syscalls use a metadata to define the fields. I moved the fields list from the event to the metadata and added a "get_fields()" function to the class. This function is used to find the fields. For normal events and kprobes, get_fields() just returns a pointer to the fields list_head in the class. For syscall events, it returns the fields list_head in the metadata for the event. v2: Fixed the syscall fields. The syscall metadata needs a list of fields for both enter and exit. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 22:35:55 +08:00
.define_fields = ftrace_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_##call.fields),\
.raw_init = trace_event_raw_init, \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
.probe = ftrace_raw_event_##call, \
.reg = ftrace_event_reg, \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
_TRACE_PERF_INIT(call) \
};
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
\
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
static struct ftrace_event_call __used event_##call = { \
.class = &event_class_##template, \
{ \
.tp = &__tracepoint_##call, \
}, \
.event.funcs = &ftrace_event_type_funcs_##template, \
.print_fmt = print_fmt_##template, \
.flags = TRACE_EVENT_FL_TRACEPOINT, \
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
}; \
static struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
tracing: add raw trace point recording infrastructure Impact: lower overhead tracing The current event tracer can automatically pick up trace points that are registered with the TRACE_FORMAT macro. But it required a printf format string and parsing. Although, this adds the ability to get guaranteed information like task names and such, it took a hit in overhead processing. This processing can add about 500-1000 nanoseconds overhead, but in some cases that too is considered too much and we want to shave off as much from this overhead as possible. Tom Zanussi recently posted tracing patches to lkml that are based on a nice idea about capturing the data via C structs using STRUCT_ENTER, STRUCT_EXIT type of macros. I liked that method very much, but did not like the implementation that required a developer to add data/code in several disjoint locations. This patch extends the event_tracer macros to do a similar "raw C" approach that Tom Zanussi did. But instead of having the developers needing to tweak a bunch of code all over the place, they can do it all in one macro - preferably placed near the code that it is tracing. That makes it much more likely that tracepoints will be maintained on an ongoing basis by the code they modify. The new macro TRACE_EVENT_FORMAT is created for this approach. (Note, a developer may still utilize the more low level DECLARE_TRACE macros if they don't care about getting their traces automatically in the event tracer.) They can also use the existing TRACE_FORMAT if they don't need to code the tracepoint in C, but just want to use the convenience of printf. So if the developer wants to "hardwire" a tracepoint in the fastest possible way, and wants to acquire their data via a user space utility in a raw binary format, or wants to see it in the trace output but not sacrifice any performance, then they can implement the faster but more complex TRACE_EVENT_FORMAT macro. Here's what usage looks like: TRACE_EVENT_FORMAT(name, TPPROTO(proto), TPARGS(args), TPFMT(fmt, fmt_args), TRACE_STUCT( TRACE_FIELD(type1, item1, assign1) TRACE_FIELD(type2, item2, assign2) [...] ), TPRAWFMT(raw_fmt) ); Note name, proto, args, and fmt, are all identical to what TRACE_FORMAT uses. name: is the unique identifier of the trace point proto: The proto type that the trace point uses args: the args in the proto type fmt: printf format to use with the event printf tracer fmt_args: the printf argments to match fmt TRACE_STRUCT starts the ability to create a structure. Each item in the structure is defined with a TRACE_FIELD TRACE_FIELD(type, item, assign) type: the C type of item. item: the name of the item in the stucture assign: what to assign the item in the trace point callback raw_fmt is a way to pretty print the struct. It must match the order of the items are added in TRACE_STUCT An example of this would be: TRACE_EVENT_FORMAT(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p, int success), TPARGS(rq, p, success), TPFMT("task %s:%d %s", p->comm, p->pid, success?"succeeded":"failed"), TRACE_STRUCT( TRACE_FIELD(pid_t, pid, p->pid) TRACE_FIELD(int, success, success) ), TPRAWFMT("task %d success=%d") ); This creates us a unique struct of: struct { pid_t pid; int success; }; And the way the call back would assign these values would be: entry->pid = p->pid; entry->success = success; The nice part about this is that the creation of the assignent is done via macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is created, the developer will then have a faster method to record into the ring buffer. They do not need to worry about the tracer itself. The developer would only need to touch the files in include/trace/*.h Again, I would like to give special thanks to Tom Zanussi for this nice idea. Idea-from: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-02-28 08:12:30 +08:00
\
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
static char print_fmt_##call[] = print; \
\
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
static struct ftrace_event_call __used event_##call = { \
.class = &event_class_##template, \
{ \
.tp = &__tracepoint_##call, \
}, \
.event.funcs = &ftrace_event_type_funcs_##call, \
.print_fmt = print_fmt_##call, \
.flags = TRACE_EVENT_FL_TRACEPOINT, \
tracing: Replace trace_event struct array with pointer array Currently the trace_event structures are placed in the _ftrace_events section, and at link time, the linker makes one large array of all the trace_event structures. On boot up, this array is read (much like the initcall sections) and the events are processed. The problem is that there is no guarantee that gcc will place complex structures nicely together in an array format. Two structures in the same file may be placed awkwardly, because gcc has no clue that they are suppose to be in an array. A hack was used previous to force the alignment to 4, to pack the structures together. But this caused alignment issues with other architectures (sparc). Instead of packing the structures into an array, the structures' addresses are now put into the _ftrace_event section. As pointers are always the natural alignment, gcc should always pack them tightly together (otherwise initcall, extable, etc would also fail). By having the pointers to the structures in the section, we can still iterate the trace_events without causing unnecessary alignment problems with other architectures, or depending on the current behaviour of gcc that will likely change in the future just to tick us kernel developers off a little more. The _ftrace_event section is also moved into the .init.data section as it is now only needed at boot up. Suggested-by: David Miller <davem@davemloft.net> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
}; \
static struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef TRACE_SYSTEM_VAR
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#ifdef CONFIG_PERF_EVENTS
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#undef __entry
#define __entry entry
#undef __get_dynamic_array
#define __get_dynamic_array(field) \
((void *)__entry + (__entry->__data_loc_##field & 0xffff))
#undef __get_dynamic_array_len
#define __get_dynamic_array_len(field) \
((__entry->__data_loc_##field >> 16) & 0xffff)
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __get_bitmask
#define __get_bitmask(field) (char *)__get_dynamic_array(field)
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#undef __perf_addr
#define __perf_addr(a) (__addr = (a))
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#undef __perf_count
#define __perf_count(c) (__count = (c))
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#undef __perf_task
#define __perf_task(t) (__task = (t))
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace void \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
perf_trace_##call(void *__data, proto) \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
{ \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
struct ftrace_event_call *event_call = __data; \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ftrace_raw_##call *entry; \
perf: Avoid horrible stack usage Both Linus (most recent) and Steve (a while ago) reported that perf related callbacks have massive stack bloat. The problem is that software events need a pt_regs in order to properly report the event location and unwind stack. And because we could not assume one was present we allocated one on stack and filled it with minimal bits required for operation. Now, pt_regs is quite large, so this is undesirable. Furthermore it turns out that most sites actually have a pt_regs pointer available, making this even more onerous, as the stack space is pointless waste. This patch addresses the problem by observing that software events have well defined nesting semantics, therefore we can use static per-cpu storage instead of on-stack. Linus made the further observation that all but the scheduler callers of perf_sw_event() have a pt_regs available, so we change the regular perf_sw_event() to require a valid pt_regs (where it used to be optional) and add perf_sw_event_sched() for the scheduler. We have a scheduler specific call instead of a more generic _noregs() like construct because we can assume non-recursion from the scheduler and thereby simplify the code further (_noregs would have to put the recursion context call inline in order to assertain which __perf_regs element to use). One last note on the implementation of perf_trace_buf_prepare(); we allow .regs = NULL for those cases where we already have a pt_regs pointer available and do not need another. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Vaibhav Nagarnaik <vnagarnaik@google.com> Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-12-16 19:47:34 +08:00
struct pt_regs *__regs; \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
u64 __addr = 0, __count = 1; \
struct task_struct *__task = NULL; \
struct hlist_head *head; \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
int __entry_size; \
int __data_size; \
int rctx; \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
\
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
\
head = this_cpu_ptr(event_call->perf_events); \
if (__builtin_constant_p(!__task) && !__task && \
hlist_empty(head)) \
return; \
\
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
sizeof(u64)); \
__entry_size -= sizeof(u32); \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
\
entry = perf_trace_buf_prepare(__entry_size, \
event_call->event.type, &__regs, &rctx); \
if (!entry) \
return; \
\
perf: Avoid horrible stack usage Both Linus (most recent) and Steve (a while ago) reported that perf related callbacks have massive stack bloat. The problem is that software events need a pt_regs in order to properly report the event location and unwind stack. And because we could not assume one was present we allocated one on stack and filled it with minimal bits required for operation. Now, pt_regs is quite large, so this is undesirable. Furthermore it turns out that most sites actually have a pt_regs pointer available, making this even more onerous, as the stack space is pointless waste. This patch addresses the problem by observing that software events have well defined nesting semantics, therefore we can use static per-cpu storage instead of on-stack. Linus made the further observation that all but the scheduler callers of perf_sw_event() have a pt_regs available, so we change the regular perf_sw_event() to require a valid pt_regs (where it used to be optional) and add perf_sw_event_sched() for the scheduler. We have a scheduler specific call instead of a more generic _noregs() like construct because we can assume non-recursion from the scheduler and thereby simplify the code further (_noregs would have to put the recursion context call inline in order to assertain which __perf_regs element to use). One last note on the implementation of perf_trace_buf_prepare(); we allow .regs = NULL for those cases where we already have a pt_regs pointer available and do not need another. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Vaibhav Nagarnaik <vnagarnaik@google.com> Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-12-16 19:47:34 +08:00
perf_fetch_caller_regs(__regs); \
\
tstruct \
\
{ assign; } \
\
perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \
perf: Avoid horrible stack usage Both Linus (most recent) and Steve (a while ago) reported that perf related callbacks have massive stack bloat. The problem is that software events need a pt_regs in order to properly report the event location and unwind stack. And because we could not assume one was present we allocated one on stack and filled it with minimal bits required for operation. Now, pt_regs is quite large, so this is undesirable. Furthermore it turns out that most sites actually have a pt_regs pointer available, making this even more onerous, as the stack space is pointless waste. This patch addresses the problem by observing that software events have well defined nesting semantics, therefore we can use static per-cpu storage instead of on-stack. Linus made the further observation that all but the scheduler callers of perf_sw_event() have a pt_regs available, so we change the regular perf_sw_event() to require a valid pt_regs (where it used to be optional) and add perf_sw_event_sched() for the scheduler. We have a scheduler specific call instead of a more generic _noregs() like construct because we can assume non-recursion from the scheduler and thereby simplify the code further (_noregs would have to put the recursion context call inline in order to assertain which __perf_regs element to use). One last note on the implementation of perf_trace_buf_prepare(); we allow .regs = NULL for those cases where we already have a pt_regs pointer available and do not need another. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Reported-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Vaibhav Nagarnaik <vnagarnaik@google.com> Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-12-16 19:47:34 +08:00
__count, __regs, head, __task); \
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
}
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
/*
* This part is compiled out, it is only here as a build time check
* to make sure that if the tracepoint handling changes, the
* perf probe will fail to compile unless it too is updated.
*/
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
perf: Fetch hot regs from the template caller Trace events can be defined from a template using DECLARE_EVENT_CLASS/DEFINE_EVENT or directly with TRACE_EVENT. In both cases we have a template tracepoint handler, used to record the trace, to which we pass our ftrace event instance. In the function level, if the class is named "foo" and the event is named "blah", we have the following chain of calls: perf_trace_blah() -> perf_trace_templ_foo() In the case we have several events sharing the class "blah", we'll have multiple users of perf_trace_templ_foo(), and it won't be inlined by the compiler. This is usually what happens with the DECLARE_EVENT_CLASS/DEFINE_EVENT based definition. But if perf_trace_blah() is the only caller of perf_trace_templ_foo() there are fair chances that it will be inlined. The problem is that we fetch the regs from perf_trace_templ_foo() after we rewinded the frame pointer to the second caller, we want to reach the caller of perf_trace_blah() to get the right source of the event. And we do this by always assuming that perf_trace_templ_foo() is not inlined. But as shown above this is not always true. And if it is inlined we miss the first caller, losing the most important level of precision. We get: 61.31% ls [kernel.kallsyms] [k] do_softirq | --- do_softirq irq_exit do_IRQ common_interrupt | |--25.00%-- tty_buffer_request_room Instead of: 61.31% ls [kernel.kallsyms] [k] __do_softirq | --- __do_softirq do_softirq irq_exit do_IRQ common_interrupt | |--25.00%-- tty_buffer_request_room To fix this, we fetch the regs from perf_trace_blah() rather than perf_trace_templ_foo() so that we don't have to deal with inlining surprises. That also bring us the advantage of having the true source of the event even if we don't have frame pointers. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@elte.hu>
2010-03-19 08:23:53 +08:00
#define DEFINE_EVENT(template, call, proto, args) \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
static inline void perf_test_probe_##call(void) \
perf: Fetch hot regs from the template caller Trace events can be defined from a template using DECLARE_EVENT_CLASS/DEFINE_EVENT or directly with TRACE_EVENT. In both cases we have a template tracepoint handler, used to record the trace, to which we pass our ftrace event instance. In the function level, if the class is named "foo" and the event is named "blah", we have the following chain of calls: perf_trace_blah() -> perf_trace_templ_foo() In the case we have several events sharing the class "blah", we'll have multiple users of perf_trace_templ_foo(), and it won't be inlined by the compiler. This is usually what happens with the DECLARE_EVENT_CLASS/DEFINE_EVENT based definition. But if perf_trace_blah() is the only caller of perf_trace_templ_foo() there are fair chances that it will be inlined. The problem is that we fetch the regs from perf_trace_templ_foo() after we rewinded the frame pointer to the second caller, we want to reach the caller of perf_trace_blah() to get the right source of the event. And we do this by always assuming that perf_trace_templ_foo() is not inlined. But as shown above this is not always true. And if it is inlined we miss the first caller, losing the most important level of precision. We get: 61.31% ls [kernel.kallsyms] [k] do_softirq | --- do_softirq irq_exit do_IRQ common_interrupt | |--25.00%-- tty_buffer_request_room Instead of: 61.31% ls [kernel.kallsyms] [k] __do_softirq | --- __do_softirq do_softirq irq_exit do_IRQ common_interrupt | |--25.00%-- tty_buffer_request_room To fix this, we fetch the regs from perf_trace_blah() rather than perf_trace_templ_foo() so that we don't have to deal with inlining surprises. That also bring us the advantage of having the true source of the event even if we don't have frame pointers. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@elte.hu>
2010-03-19 08:23:53 +08:00
{ \
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
check_trace_callback_type_##call(perf_trace_##template); \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
}
tracing: Remove per event trace registering This patch removes the register functions of TRACE_EVENT() to enable and disable tracepoints. The registering of a event is now down directly in the trace_events.c file. The tracepoint_probe_register() is now called directly. The prototypes are no longer type checked, but this should not be an issue since the tracepoints are created automatically by the macros. If a prototype is incorrect in the TRACE_EVENT() macro, then other macros will catch it. The trace_event_class structure now holds the probes to be called by the callbacks. This removes needing to have each event have a separate pointer for the probe. To handle kprobes and syscalls, since they register probes in a different manner, a "reg" field is added to the ftrace_event_class structure. If the "reg" field is assigned, then it will be called for enabling and disabling of the probe for either ftrace or perf. To let the reg function know what is happening, a new enum (trace_reg) is created that has the type of control that is needed. With this new rework, the 82 kernel events and 618 syscall events has their footprint dramatically lowered: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint 4900252 1057412 861512 6819176 680d68 vmlinux.regs The size went from 6863829 to 6819176, that's a total of 44K in savings. With tracepoints being continuously added, this is critical that the footprint becomes minimal. v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf specific structure in trace_events.c. v4: Fixed trace self tests to check probe because regfunc no longer exists. v3: Updated to handle void *data in beginning of probe parameters. Also added the tracepoint: check_trace_callback_type_##call(). v2: Changed the callback probes to pass void * and typecast the value within the function. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-22 00:27:06 +08:00
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#endif /* CONFIG_PERF_EVENTS */
perf_counter: Fix/complete ftrace event records sampling This patch implements the kernel side support for ftrace event record sampling. A new counter sampling attribute is added: PERF_SAMPLE_TP_RECORD which requests ftrace events record sampling. In this case if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint fires, we emit the tracepoint binary record to the perfcounter event buffer, as a sample. Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf record: perf record -f -F 1 -a -e workqueue:workqueue_execution perf report -D 0x21e18 [0x48]: event: 9 . . ... raw event: size 72 bytes . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........ . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!...... . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1........... . 0040: e0 b1 31 81 ff ff ff ff ....... . 0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33 The raw ftrace binary record starts at offset 0020. Translation: struct trace_entry { type = 0x2b = 43; flags = 1; preempt_count = 2; pid = 0xa = 10; tgid = 0xa = 10; } thread_comm = "events/1" thread_pid = 0xa = 10; func = 0xffffffff8131b1e0 = flush_to_ldisc() What will come next? - Userspace support ('perf trace'), 'flight data recorder' mode for perf trace, etc. - The unconditional copy from the profiling callback brings some costs however if someone wants no such sampling to occur, and needs to be fixed in the future. For that we need to have an instant access to the perf counter attribute. This is a matter of a flag to add in the struct ftrace_event. - Take care of the events recursivity! Don't ever try to record a lock event for example, it seems some locking is used in the profiling fast path and lead to a tracing recursivity. That will be fixed using raw spinlock or recursivity protection. - [...] - Profit! :-) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-07 07:25:54 +08:00